MOT16 Results

Click on a measure to sort the table accordingly. See below for a more detailed description.

TrackerAvg RankMOTAMOTPFAFMTMLFPFNID Sw.FragHzDetector
NOMTwSDP16
1. new
2.3
60.2
±12.1
79.51.225.9% 38.6% 6,94165,120428 (6.7)655 (10.2)3.1Private
W. Choi. Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor. In ICCV, 2015.
NOMT
2. using public detections
3.3
44.7
±10.8
76.41.913.1% 47.8% 11,35689,120374 (7.3)522 (10.2)2.5Public
W. Choi. Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor. In ICCV, 2015.
LINF1
3. using public detections
4.8
40.5
±10.1
74.91.410.7% 56.1% 8,40199,715426 (9.4)953 (21.0)1.1Public
Anonymous submission
TBD
4. using public detections
4.6
33.3
±9.6
76.51.06.6% 58.2% 6,160112,9502,407 (63.3)2,241 (58.9)1.3Public
A. Geiger, M. Lauer, C. Wojek, C. Stiller, R. Urtasun. 3D Traffic Scene Understanding from Movable Platforms. In Pattern Analysis and Machine Intelligence (PAMI), 2014.
CEM
5. using public detections
5.3
32.6
±8.6
75.91.37.0% 59.4% 7,415114,861634 (17.1)719 (19.4)0.3Public
A. Milan, S. Roth, K. Schindler. Continuous Energy Minimization for Multitarget Tracking. In IEEE TPAMI, 2014.
DP_NMS
6. using public detections
4.4
31.9
±9.9
76.40.24.8% 65.2% 1,343121,813969 (29.2)941 (28.4)212.6Public
H. Pirsiavash, D. Ramanan, C. Fowlkes. Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects. In CVPR, 2011.
SMOT
7. using public detections
6.7
29.2
±7.9
75.23.04.9% 53.3% 17,929108,0413,072 (75.4)4,437 (108.9)0.2Public
C. Dicle, O. Camps, M. Sznaier. The Way They Move: Tracking Targets with Similar Appearance. In ICCV, 2013.
JPDA_m
8. using public detections
4.6
25.9
±6.4
76.40.73.7% 70.4% 3,930130,799364 (12.9)634 (22.4)16.2Public
H. Rezatofighi, A. Milan, Z. Zhang, Q. Shi, A. Dick, I. Reid. Joint Probabilistic Data Association Revisited. In ICCV, 2015.

Benchmark Statistics

SequencesFramesTrajectoriesBoxes
75919830182326

Difficulty Analysis

Sequence difficulty (from easiest to hardest, measured by average MOTA)

MOT16-03

MOT16-03

(41.2% MOTA)

MOT16-06

MOT16-06

(35.8% MOTA)

MOT16-12

MOT16-12

(33.8% MOTA)

...

...

MOT16-01

MOT16-01

(25.6% MOTA)

MOT16-14

MOT16-14

(11.4% MOTA)


Evaluation Measures

Lower is better. Higher is better.
Measure Better Perfect Description
Avg Rank lower 1 This is the rank of each tracker averaged over all present evaluation measures.
MOTA higher 100 % Multiple Object Tracking Accuracy [1]. This measure combines three error sources: false positives, missed targets and identity switches.
MOTP higher 100 % Multiple Object Tracking Precision [1]. The misalignment between the annotated and the predicted bounding boxes.
FAF lower 0 The average number of false alarms per frame.
MT higher 100 % Mostly tracked targets. The ratio of ground-truth trajectories that are covered by a track hypothesis for at least 80% of their respective life span.
ML lower 0 % Mostly lost targets. The ratio of ground-truth trajectories that are covered by a track hypothesis for at most 20% of their respective life span.
FP lower 0 % The total number of false positives.
FN lower 0 The total number of false negatives (missed targets).
ID Sw. lower 0 The total number of identity switches. Please note that we follow the stricter definition of identity switches as described in [2].
Frag lower 0 The total number of times a trajectory is fragmented (i.e. interrupted during tracking).
Hz higher Inf. Processing speed (in frames per second excluding the detector) on the benchmark.

Legend

Symbol Description
online method This is an online (causal) method, i.e. the solution is immediately available with each incoming frame and cannot be changed at any later time.
using public detections This method used the provided detection set as input.
new This entry has been submitted or updated less than a week ago.

References:


[1] Bernardin, K. & Stiefelhagen, R. Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics. Image and Video Processing, 2008(1):1-10, 2008.
[2] Li, Y., Huang, C. & Nevatia, R. Learning to associate: HybridBoosted multi-target tracker for crowded scene. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009.